Assessment of artificial intelligence to detect gasoline in fire debris using HS‐SPME‐GC/MS and transfer learning

• Published in: Journal of forensic sciences Vol. 69; no. 4; pp. 1222 - 1234
• Main Authors: Huang, Ting‐Yu, Chung Yu, Jorn Chi
• Format: Journal Article
• Language: English
• Published: United States Wiley Subscription Services, Inc 01.07.2024
• Subjects: Accuracy; Artificial intelligence; Artificial neural networks; Chemical composition; convolutional neural network and CNN; Debris; fire debris analysis; Forensic chemistry; Gas chromatography; gas chromatography–mass spectrometry and GCMS; Gasoline; heatmaps; Image classification; Machine learning; solid phase microextraction and SPME; Substrates; transfer learning; Workflow; fire debris analysis; solid phase microextraction and SPME; convolutional neural network and CNN; transfer learning; heatmaps; gas chromatography–mass spectrometry and GCMS
• ISSN: 0022-1198; 1556-4029; 1556-4029
• DOI: 10.1111/1556-4029.15550

Due to the complex nature of the chemical compositions of ignitable liquids (IL) and the interferences from fire debris matrices, interpreting chromatographic data poses challenges to analysts. In this work, artificial intelligence (AI) was developed by transfer learning in a convolutional neural network (CNN), GoogLeNet. The image classification AI was fine‐tuned to create intelligent classification systems to discriminate samples containing gasoline residues from burned substrates. All ground truth samples were analyzed by headspace solid‐phase microextraction (HS‐SPME) coupled with a gas chromatograph and mass spectrometer (GC/MS). The HS‐SPME‐GC/MS data were transformed into three types of image presentations, that is, heatmaps, extracted ion heatmaps, and total ion chromatograms. The abundance and mass‐to‐charge ratios of each scan were converted into image patterns that are characteristic of the chemical profiles of gasoline. The transfer learning data were labeled as “gasoline present” and “gasoline absent” classes. The assessment results demonstrated that all AI models achieved 100 ± 0% accuracy in identifying neat gasoline. When the models were assessed using the spiked samples, the AI model developed using the extracted ion heatmap obtained the highest accuracy rate (95.9 ± 0.4%), which was greater than those obtained by other machine learning models, ranging from 17.3 ± 0.7% to 78.7 ± 0.7%. The proposed work demonstrated that the heatmaps created from GC/MS data can represent chemical features from the samples. Additionally, the pretrained CNN models are readily available in the transfer learning workflow to develop AI for GC/MS data interpretation in fire debris analysis.